Spatial Intelligence
Spatial Intelligence
  • 47
  • 408 887
I Tested Google's Veo 2... It DESTROYS Sora! (Hands-on Review)
Google's Veo 2 just redefined AI video generation. In this hands-on review, I show you why this tool is a quantum leap beyond Sora and every other AI video model -- with real testing and incredible examples from early access.
Google DeepMind's Veo 2 creates photorealistic videos with incredible physics, consistent scenes, and mind-blowing creativity. Features like native 4K output, cinematographer-friendly prompts, and superior prompt adherence make it revolutionary. Watch real examples from my community pushing the boundaries - from anime characters to historical recreations, from surreal scenes to practical motion graphics.
Learn why Google's unique training approach gives them a massive advantage in video generation. I break down all the key features, compare it with OpenAI's Sora, and show you exactly how to use tools like Whisk to get the best results. Whether you're a creator, developer, or just curious about AI advancement, this comprehensive review will keep you ahead of the curve!
00:00 Google Veo 2 Overview
01:50 Prompting Veo 2 w/ the Community
20:57 New Ways To Prompt w/ Google's Whisk + Veo 2
25:16 OpenAI Sora vs. Veo 2 - The Good & Bad
32:12 Conclusion: The Future of AI Video
Connect on socials:
- Twitter/X: x.com/bilawalsidhu
- Weekly newsletter: spatialintelligence.ai
- Other links: bilawal.ai
#ainews #aitools #artificialintelligence
มุมมอง: 34 981

วีดีโอ

Android XR Live Demo: Samsung's Headset with Gemini AI + Google's AR Glasses
มุมมอง 49K16 ชั่วโมงที่ผ่านมา
First ever live demo of Samsung’s mixed reality headset running Android XR! Gemini AI built right in, the Google apps you know and love with a very intuitive UX. The Google team crushed it, and Samsung went deep with Project Moohan taking advantage of multimodal AI for vision, touch and voice input. Also very cool to see Google maps immersive view playing a key role which I cofounded & led prod...
3 Revolutionary AI Tools Changing the Game for Interactive 3D Worlds
มุมมอง 3.9K14 วันที่ผ่านมา
3 major breakthroughs just revolutionized how AI creates 3D worlds! CAT4D brings motion to static scenes, World Labs transforms single images into explorable environments, and Genie 2 creates INTERACTIVE worlds from concept art. Here's everything you need to know about these developments in 3D AI, including their impact on game dev, VFX, and the future of film: 🎯 TIMESTAMPS: 0:00 Current Gen of...
How AI NPCs Will Change Gaming Forever (and your love life too)
มุมมอง 1.1Kหลายเดือนก่อน
AI is changing gaming, and gaming is changing the world. 10 ways AI NPCs will impact humanity forever-from education and relationships to jobs and even consciousness. Imagine video game characters so real, you can't tell the difference. It sounds like science fiction, but it's happening right now... and most people have no idea. With apps like Character AI already ranking above Disney and HBO M...
I Found a SECRET Goldmine of 3D Data! (And You Can Use It For FREE)
มุมมอง 11K2 หลายเดือนก่อน
Mosaic dropped an INSANE 15 Terapixel dataset of Prague-1.26 MILLION 360° images! This type of geospatial data was used for VFX in The Gray Man, and it's now FREE for non-commercial use. Imagine creating stunning 3D worlds, training AI models, building next-gen VR experiences, or even diving into GTA-style gaming and virtual production-all with this incredibly detailed data. This video explores...
3D Gaussian Splatting: The 4-Minute Magic Trick in After Effects
มุมมอง 3.1K3 หลายเดือนก่อน
Quick 4 minute walkthrough to get you up and running with 3D Gaussian Splatting and all the cool things you can do with Radiance Fields inside After Effects. Timestamps: 00:00 Introduction to 3DGS in AE 00:19 Integrating 3D Objects w/ Z-Depth Compositing 01:03 Adding Motion w/ 3D Camera Tracking 01:30 Applying Effects to your 3D Gaussian Splat 03:00 Current Limitations ⚙️The AE plugin i'm using...
Claude 3.5 Builds Stunning 3D Website Using Three.js
มุมมอง 1K4 หลายเดือนก่อน
Quick tip: Use Claude Artifacts with Three.js to create 3D graphics on the web. I started with a basic hypercube animation. Then I challenged Claude to be a '10x coder'. And to my surprise, it delivered an extremely elevated redesign! Pretty wild. You can do in 30 minutes what previously took a day of work. Now if only Claude had a higher rate limit! Twitter: x.com/bilawalsidhu Website: www.bil...
Is Apple AI the END of Privacy? (Elon Musk Thinks So)
มุมมอง 6066 หลายเดือนก่อน
Apple BIG push into AI is here... but Elon Musk is calling it SPYWARE. Is he right? Or is Tim Cook playing 4D chess and setting the stage for AR glasses and neural Airpods? In this video, we go DEEPER than the hype and actually BREAK DOWN Apple's new AI strategy. Forget the surface-level influencer summaries - we're diving into the technical details: on-device AI, Apple's private cloud compute,...
Helen Toner on Firing Sam Altman - What REALLY Happened at OpenAI
มุมมอง 5K6 หลายเดือนก่อน
What REALLY happened at OpenAI? Former board member Helen Toner breaks her silence with shocking new details about Sam Altman's firing. Hear the exclusive, untold story on The TED AI Show: link.chtbl.com/TEDAI I went into this convo expecting an AI policy maximalist, but found Helen Toner to be much more nuanced (and fascinating). Listen to Helen's take on OpenAI, self-governance, AI policy, an...
NVIDIA's Mind-Blowing Spatial Computing Revolution!
มุมมอง 14K8 หลายเดือนก่อน
Exclusive interview with David Chu, VP of Spatial Computing & XR at NVIDIA, at GTC 2024! David shares his insights on the future of technology, where spatial computing and AI converge to blur the lines between the physical and digital worlds. Discover how NVIDIA's groundbreaking tools like Omniverse, CloudXR, NeMo and the AI assistant platform, Tokkio, are empowering creators, developers, and b...
Apple Vision Pro 100 Hours Later: The Good, Bad, and Ugly
มุมมอง 7K9 หลายเดือนก่อน
I spent over 100 hours using the Apple Vision Pro, and while it has some amazing features, there are also things Apple got seriously wrong. From a wonky telepresence experience to limited immersive video options, this in-depth review dives into the good, the bad, and the broken after extensive use. Is the Vision Pro truly revolutionary or just a glorified iPad? Watch and find out! Connect on so...
Top Gun's CGI Secret: 2,400 Shots You Didn't Notice
มุมมอง 3.3K10 หลายเดือนก่อน
At first glance, Top Gun Maverick's heart-pounding aerial scenes look 100% real. But behind the IMAX-filmed cockpit closeups lies an elaborate VFX effort few viewers noticed. By blending real jet footage with meticulously crafted CGI models, the Top Gun VFX crew pulled an elaborate illusion. Learn how they created photorealistic animations, matched real jet lighting, and added danger-free forma...
Apple Vision Pro: The VR Wars Have Begun! ft. Ben Lang (Road to VR)
มุมมอง 2.4K10 หลายเดือนก่อน
Apple vs. Android: the battle for spatial supremacy starts now. Unveiling the real advantage of Apple Vision Pro: its insane hardware specs and seamless ecosystem integration. We'll dissect what sets it apart from rivals and how its absence of mainstream apps like Netflix and TH-cam could signal a major market shift. Featuring Special Guest: Ben Lang, XR Analyst & Co-Founder @ Road to VR. Video...
Google Lumiere AI: Space-Time Video Diffusion Explained!
มุมมอง 1.4K10 หลายเดือนก่อน
Google Lumiere AI: Space-Time Video Diffusion Explained!
3D Scanning Changed Again. NeRFs Are SO Back!
มุมมอง 16K11 หลายเดือนก่อน
3D Scanning Changed Again. NeRFs Are SO Back!
They Built The AI Panopticon And You’re Already In It
มุมมอง 85911 หลายเดือนก่อน
They Built The AI Panopticon And You’re Already In It
Google's Insane Data Moat + Multimodal AI Juggernaut
มุมมอง 71711 หลายเดือนก่อน
Google's Insane Data Moat Multimodal AI Juggernaut
10 Things You Can Do With 3D Gaussian Splatting & Reality Capture
มุมมอง 46Kปีที่แล้ว
10 Things You Can Do With 3D Gaussian Splatting & Reality Capture
3D Gaussian Splatting - Explained!
มุมมอง 103Kปีที่แล้ว
3D Gaussian Splatting - Explained!
NVIDIA Exec Shares Plans To Simulate The Real World With AI 🌐
มุมมอง 2Kปีที่แล้ว
NVIDIA Exec Shares Plans To Simulate The Real World With AI 🌐
Elon Musk's xAI vs OpenAI & Google - Who Will Win the AI Race?
มุมมอง 3.6Kปีที่แล้ว
Elon Musk's xAI vs OpenAI & Google - Who Will Win the AI Race?
Elon Musk's Grand Plan For X - Explained!
มุมมอง 10Kปีที่แล้ว
Elon Musk's Grand Plan For X - Explained!
Kris Kashtanova on AI Art, Copyright Battles, & Community Building
มุมมอง 174ปีที่แล้ว
Kris Kashtanova on AI Art, Copyright Battles, & Community Building
Hilmar Koch: How an Academy Award Winning VFX Wizard Got Into Computer Graphics & Virtual Production
มุมมอง 128ปีที่แล้ว
Hilmar Koch: How an Academy Award Winning VFX Wizard Got Into Computer Graphics & Virtual Production
Ep 2: ChatGPT & Teachers, AI Art Lawsuits Drop, Meta Teases Text-to-4D Video, Google Touts AI Audio
มุมมอง 125ปีที่แล้ว
Ep 2: ChatGPT & Teachers, AI Art Lawsuits Drop, Meta Teases Text-to-4D Video, Google Touts AI Audio
Is The Generative AI Hype Real? | Creative Technology Podcast EP#01
มุมมอง 415ปีที่แล้ว
Is The Generative AI Hype Real? | Creative Technology Podcast EP#01
The Rise of the Metaverse: A 30-Minute Deep Dive
มุมมอง 4972 ปีที่แล้ว
The Rise of the Metaverse: A 30-Minute Deep Dive

ความคิดเห็น

  • @salo1129
    @salo1129 6 ชั่วโมงที่ผ่านมา

    What’s up with all the latent space useage.

  • @contentfreeGPT5-py6uv
    @contentfreeGPT5-py6uv 8 ชั่วโมงที่ผ่านมา

    AND apple Disney Cyberpunk dancing no the Júpiter qnd blabla AND athromoephic cars2060 with 5 dimensión

  • @sloanNYC
    @sloanNYC 8 ชั่วโมงที่ผ่านมา

    AR Glasses are where companies should focus ASAP. Apple should jump here immediately. It looks like the AR glasses shown in these demo videos are not near ready. The fidelity and size of the heads up graphics are likely not available at a decent price yet. Hearview has some glasses that do live captions already but are over $1,000. I look forward to people being able to have menus read to them, using LiDAR and spatial awareness to help vision impaired navigate spaces, live captions and translations... directions to a store. There are lots of great features that can be ready next year.

  • @strength9621
    @strength9621 9 ชั่วโมงที่ผ่านมา

    Though Google may surpass chat gpt, they'll still have the issue of have they absolutely fragment all of their services making it harder to use vs most of what chat gpt offers is on one location. The latter makes it easier for a normie to use, and thats where the majority wil be, and that's who will win. Hopefully they get this right,

    • @spatialintel
      @spatialintel 19 นาทีที่ผ่านมา

      Agree. Google needs to be better at this. And not kludge it into some dev tool either.

  • @strength9621
    @strength9621 9 ชั่วโมงที่ผ่านมา

    im glad Sora didnt cost an extra fee because it is TRASH, I cant believe I waited so long for it smh,

  • @maddavisdog07
    @maddavisdog07 9 ชั่วโมงที่ผ่านมา

    This and AR coming together is going to get crazy

    • @spatialintel
      @spatialintel 20 นาทีที่ผ่านมา

      Akin to reskinning reality

  • @FiveMCity
    @FiveMCity 10 ชั่วโมงที่ผ่านมา

    Hunyuan is not free guys.. you get 1 credit and "service not available in your country", USA, for Google ImageFX.

  • @XMCRacing
    @XMCRacing 10 ชั่วโมงที่ผ่านมา

    Now we know why it took so long for Sora to come out. They knew it was garbage.

  • @Averageca
    @Averageca 10 ชั่วโมงที่ผ่านมา

    Feel bad for all of the 3d renders out there

  • @VitzAnim
    @VitzAnim 11 ชั่วโมงที่ผ่านมา

    Wow! Not even sure I want to animate anymore lol, this ai made 10 times what I could do in a couple seconds lol, bye animating!

    • @spatialintel
      @spatialintel 20 นาทีที่ผ่านมา

      Keep animation - now just set your sights on creating a short or movie instead of a shot

  • @darrenstettner5381
    @darrenstettner5381 12 ชั่วโมงที่ผ่านมา

    No one asked for Miss Fortune to have nipples ado do jumping jacks?

  • @truthspeaker7878
    @truthspeaker7878 12 ชั่วโมงที่ผ่านมา

    u have more control over prompt detail but it still looks ai and smeary and saturated with over color. sora looks better, but less director control

    • @spatialintel
      @spatialintel 12 ชั่วโมงที่ผ่านมา

      yeah sora def has a nice look out of the box - it's the physics that are wonky. hopefully they roll out a bigger/slower model that is closer to the OG sora quality.

  • @truthspeaker7878
    @truthspeaker7878 13 ชั่วโมงที่ผ่านมา

    sora looks better lol

  • @polokucoch8112
    @polokucoch8112 14 ชั่วโมงที่ผ่านมา

    If this is the baseline now then in a few years eveerything will be on par with cinema. Scary to think about.

  • @Endelean
    @Endelean 16 ชั่วโมงที่ผ่านมา

    Bro how is this creating videos so perfectly when most still image generations still get 6 fingered hands?

    • @spatialintel
      @spatialintel 15 ชั่วโมงที่ผ่านมา

      most SOTA image models are pretty darn good with fingers now -- still not perfect, but the hit rate is MUCH better than it was last year

  • @scumpuppies
    @scumpuppies 16 ชั่วโมงที่ผ่านมา

    Seems better than Sora, albeit somewhat marginally.

  • @laptopkulinux5465
    @laptopkulinux5465 17 ชั่วโมงที่ผ่านมา

    now i can make my own movies ....

  • @inyapr3557
    @inyapr3557 17 ชั่วโมงที่ผ่านมา

    As an european, I can testify we indeed eat our soups like Sora showed

  • @fatalradius
    @fatalradius 17 ชั่วโมงที่ผ่านมา

    Excellent work by Google. As long as they keep their politics out of their tech they will be even much better.

  • @tenle168
    @tenle168 22 ชั่วโมงที่ผ่านมา

    2000s: hey check to see if that is photoshopped 2030s: hey check to see if that is generated by AI

    • @strength9621
      @strength9621 9 ชั่วโมงที่ผ่านมา

      2060s: hey check to see if that is a naturally generated human.

  • @perelium-x
    @perelium-x 22 ชั่วโมงที่ผ่านมา

    This is getting CRAZY. Think about this in 3-5 years.... it will be no different from real life. Even now its hard to spot

    • @spatialintel
      @spatialintel 18 ชั่วโมงที่ผ่านมา

      Feels a year away from video fully shattering the video Turing test

    • @perelium-x
      @perelium-x 17 ชั่วโมงที่ผ่านมา

      @@spatialintel Its absolutely terrifying what they can achieve. I can't even begin to imagine the complexity to build such a system

  • @davidbellemare2909
    @davidbellemare2909 22 ชั่วโมงที่ผ่านมา

    Thank you this is dope

  • @davidbellemare2909
    @davidbellemare2909 22 ชั่วโมงที่ผ่านมา

    Nice to connect brother, I spent 10 years as a global executive at Yahoo! Nice to discover your channel friend... namaste love this content, gracias!

    • @spatialintel
      @spatialintel 18 ชั่วโมงที่ผ่านมา

      Welcome brother

  • @corex72
    @corex72 วันที่ผ่านมา

    I have a bunch of script ideas that I’ve been working on since I’ve had ChatGPT. They aren’t finished. They’re just conversations with the AI right now. But I could get it to export a couple of short scripts if you’re looking for a script for your short film.

  • @Vadhin
    @Vadhin วันที่ผ่านมา

    Demon voice on 5:28 😮

  • @PromptKing
    @PromptKing วันที่ผ่านมา

    Yea Open Ai gone have to drop that price google is killing them

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      Google having their own TPUs is a huge advantage too

    • @PromptKing
      @PromptKing วันที่ผ่านมา

      @spatialintel using CUDA cores, and to think about it I only have a Titan X pascal I can only perform so many matrix till my GPU is exhausted, it puts your entire system in an optimized state of process to its maximum potential CPU and GPU communication in overdrive

    • @PromptKing
      @PromptKing วันที่ผ่านมา

      @spatialintel I'm about to change the world of processing, I'm testing my CUDA application in Blender, this application puts your CPU and GPU communication in overdrive x10 the only thing I have to fix is when you render in Blender with cycles I'm getting an error I should find a way around it soon, compiling for all NVIDA GPUs will be releasing in the store soon, note this works for all applications, I have to find why DirectX is crashing also works flawlessly in Unreal Engine testing all sorts of apps

  • @JesusAlvarado-ku5ql
    @JesusAlvarado-ku5ql วันที่ผ่านมา

    When will this products be released and how much will they cost

  • @Tobi_A
    @Tobi_A วันที่ผ่านมา

    Open AI took a massive L with the Sora thing

  • @jtuttah
    @jtuttah วันที่ผ่านมา

    The creative applications of text to video never made a whole lot of sense with models up until now. I'm absolutely stunned by how fast researchers have been able to get text to video working so well. Great work Google.

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      Me too! I still want more than text2video, but damn is it far more useful when you make prompt adherence a lot better

  • @howtomakeawebsitetherightw6573
    @howtomakeawebsitetherightw6573 วันที่ผ่านมา

    OpenAI deserves the fall, I was so excited when OpenAI introduced SORA they should release it sooner

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      If they had launched in summer it would have been the leader for a while; then again the Chinese models like Kling and minimax kinda stole that thunder already

  • @andreaskrbyravn855
    @andreaskrbyravn855 วันที่ผ่านมา

    goodbye stuntmen

  • @gamegoof
    @gamegoof วันที่ผ่านมา

    Sooooo glad Im out of the games industry, I got to experience the pre-2008 fun, lots of money, no outsourcing but now with this? No point in getting into 3d art anymore

  • @DJ-Illuminate
    @DJ-Illuminate วันที่ผ่านมา

    I watch this and assume all of them will have these same features and ability soon.

  • @ralphdelgado8232
    @ralphdelgado8232 วันที่ผ่านมา

    Can you film me a music video. I’ll pay you for it

  • @RetroDegenerate
    @RetroDegenerate วันที่ผ่านมา

    I have been waiting so long for ai to be this good

  • @EdAnde
    @EdAnde วันที่ผ่านมา

    Not to be all per say critical…but when ai creates videos allow Humans to BREATH like the motion of breathing , then it will be 👌👌👌

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      It’s funny I was talking to my friend Allie about this who observed she can’t get Veo or any model to create a sneeze - and I wondered if that’s because people cut sneezes out of their videos so it’s not in the training data 😂

    • @EdAnde
      @EdAnde วันที่ผ่านมา

      @@spatialintel 😂😂 that’s interesting! I actually didn’t think about sneezing! Makes me think about what other human abilities ai hasn’t quite got a handle on yet

  • @allisthemoist2244
    @allisthemoist2244 วันที่ผ่านมา

    It's nice that China is still losing despite all their unethical practices

  • @holdthetruthhostage
    @holdthetruthhostage วันที่ผ่านมา

    Bro if there is a way to get i to remember characters & Locations its over, as well as 20 - 60 Seconds

  • @fitybux4664
    @fitybux4664 วันที่ผ่านมา

    Hi. Please send help. I loaded up labs. I've become a MusixFX DJ nearly instantly. Help, I am stuck at the computer. It is too awesome. 😆 🤖

  • @anatalelectronics4096
    @anatalelectronics4096 วันที่ผ่านมา

    how can it literally be your moms dog?

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      Because I tossed real images of her dog into Google whisk and it’s reverse engineered images to the point that she can’t tell it’s not him

  • @malootua2739
    @malootua2739 วันที่ผ่านมา

    You know what I see happening? I see people just completely turning away from watching internet videos because we won't know if anything that we see is even real anymore, so it'll be a huge turn off, and people will just get bored, and want REAL first-hand REALITY again

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      IMO it’ll be about the value of the content - not how it was made. Simultaneously, we’ll have a Whole Foods market - but my guess is most will be down with Mountain Dew straight to the vein, which is what shorts/tt/reels feels like anyway

    • @anatalelectronics4096
      @anatalelectronics4096 วันที่ผ่านมา

      is that why hollywood does not make movies anymore?

    • @desu38
      @desu38 วันที่ผ่านมา

      sounds like a blessing in disguise, tbh

    • @williamdorsey904
      @williamdorsey904 วันที่ผ่านมา

      It will be hard to tell what's real and what's BS. Soon, we will need government approve news channels that's free from BS

    • @MysteriousLand-f1u
      @MysteriousLand-f1u วันที่ผ่านมา

      Spot on. 😂

  • @IBADSNU
    @IBADSNU วันที่ผ่านมา

    There are many things this could be used for, especially as the technology matures, but when I see this, I’m immediately excited about the future of virtual reality. I understand that this type of technology is still in its infancy, but when I think about what it will be capable of, combined with conversational AI and real-time adaptation, I feel like a kid standing in the distance, watching a theme park being developed. I might be a bit overly optimistic, but I think we're starting to get close. If you disagree, please keep it to yourself. Don't be a wet blanket. Nobody likes you. 😅

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      Absolutely. It feels like speaking worlds into existence. And I can’t wait for the convergence of 3D + AI tech.

  • @flcamera
    @flcamera วันที่ผ่านมา

    I was excited to try it out but couldn't sign in, so sadly I signed up for when the general public are let in, :(

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      Yeah, that's a shame. I hope they open it up soon, too! Meanwhile try Google whisk and imagefx

  • @JackCarter9
    @JackCarter9 วันที่ผ่านมา

    Hunyuan isn't free. You have to buy credits to generate prompts.

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      The model weights are available for free on GitHub, but you obviously need a machine local or cloud hosted to run it.

  • @DraxisWuf
    @DraxisWuf วันที่ผ่านมา

    China has petabytes of CCTV video to train with

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      Which makes them great at emulating CCTV footage?

  • @Kristianpont
    @Kristianpont วันที่ผ่านมา

    I am sure google is adding some kind of watermark in these videos, or other way of identification. They don't want to pollute their training material with already AI generated content.

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      Yes they are - Google calls it SynthID

  • @alteredalley
    @alteredalley วันที่ผ่านมา

    Wow

  • @vitusomni1983
    @vitusomni1983 วันที่ผ่านมา

    great vid soon we will be able to prototype movie scenes instead of explaining eFin storyboards.

  • @randomnumbers84269
    @randomnumbers84269 วันที่ผ่านมา

    So when do we get to use it ourselves?

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      Apparently Veo is coming to TH-cam next year; that’s been announced - videofx tool release no date shared rn

  • @lzmihich
    @lzmihich วันที่ผ่านมา

    No upload of your own image allowed for image to vídeo , makes hard to have any use for professional use. From the video professional , point of view, they need more resources

    • @spatialintel
      @spatialintel วันที่ผ่านมา

      I asked about this and it’s def on the roadmap - i suspect they wanna make sure 31:53 doesn’t happen 😂